Which of the following are correct statement(s) about stacking? 1. A machine learning model is trained on predictions of multiple machine learning models 2. A Logistic regression will definitely work better in the second stage as compared to other classification methods 3. First stage models are trained on full / partial feature space of training data.

The correct answer is: C. 1 and 3

Stacking is a machine learning technique where the predictions of multiple machine learning models are used as input to a meta-model. The meta-model then uses these predictions to make a final prediction.

There are two main stages in stacking:

1. The first stage involves training a number of base models on the original data. These models can be of any type, such as decision trees, support vector machines, or neural networks.
2. The second stage involves training a meta-model on the predictions of the base models. The meta-model can also be of any type, but it is often a simple model such as a linear regression or a decision tree.

Stacking has been shown to improve the performance of machine learning models on a variety of tasks. It is particularly useful when the base models are trained on different subsets of the data or when they have different strengths and weaknesses.

Option 1 is correct because the meta-model in stacking is trained on the predictions of multiple machine learning models.

Option 2 is incorrect because there is no guarantee that a logistic regression will work better in the second stage as compared to other classification methods. The choice of meta-model depends on the specific task and the data.

Option 3 is correct because the first stage models are trained on the original data, which may include a full or partial feature space.